bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0620
- Precision: 0.9328
- Recall: 0.9512
- F1: 0.9419
- Accuracy: 0.9864
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0878 | 1.0 | 1756 | 0.0768 | 0.9152 | 0.9298 | 0.9224 | 0.9809 |
| 0.0334 | 2.0 | 3512 | 0.0654 | 0.9239 | 0.9482 | 0.9359 | 0.9855 |
| 0.0172 | 3.0 | 5268 | 0.0620 | 0.9328 | 0.9512 | 0.9419 | 0.9864 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 106
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Dataset used to train Vibharkchauhan/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.933
- Recall on conll2003validation set self-reported0.951
- F1 on conll2003validation set self-reported0.942
- Accuracy on conll2003validation set self-reported0.986